From bedbef8ad3e75a304af6361af235302bcc61d06b Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 14 May 2024 06:39:01 +0000
Subject: [PATCH] 修改内核路径
---
kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 989 +++++++++++++++++++++++++++++++++------------------------
1 files changed, 577 insertions(+), 412 deletions(-)
diff --git a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ef92438..2b100b7 100644
--- a/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/kernel/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -27,6 +27,8 @@
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/atomic.h>
+#include <linux/numa.h>
+#include <generated/utsrelease.h>
#include <scsi/fc/fc_fcoe.h>
#include <net/udp_tunnel.h>
#include <net/pkt_cls.h>
@@ -34,13 +36,16 @@
#include <net/tc_act/tc_mirred.h>
#include <net/vxlan.h>
#include <net/mpls.h>
+#include <net/xdp_sock_drv.h>
#include <net/xfrm.h>
#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
+#include "ixgbe_phy.h"
#include "ixgbe_sriov.h"
#include "ixgbe_model.h"
+#include "ixgbe_txrx_common.h"
char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
@@ -52,8 +57,6 @@
static char ixgbe_default_device_descr[] =
"Intel(R) 10 Gigabit Network Connection";
#endif
-#define DRV_VERSION "5.1.0-k"
-const char ixgbe_driver_version[] = DRV_VERSION;
static const char ixgbe_copyright[] =
"Copyright (c) 1999-2016 Intel Corporation.";
@@ -160,8 +163,7 @@
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE("GPL v2");
static struct workqueue_struct *ixgbe_wq;
@@ -894,8 +896,8 @@
}
}
-static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
- u64 qmask)
+void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
+ u64 qmask)
{
u32 mask;
@@ -1393,7 +1395,7 @@
IXGBE_DCA_CTRL_DCA_MODE_CB2);
break;
}
- /* fall through - DCA is disabled. */
+ fallthrough; /* DCA is disabled. */
case DCA_PROVIDER_REMOVE:
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
dca_remove_requester(dev);
@@ -1674,9 +1676,9 @@
* order to populate the hash, checksum, VLAN, timestamp, protocol, and
* other fields within the skb.
**/
-static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
- union ixgbe_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
{
struct net_device *dev = rx_ring->netdev;
u32 flags = rx_ring->q_vector->adapter->flags;
@@ -1709,8 +1711,8 @@
skb->protocol = eth_type_trans(skb, dev);
}
-static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
- struct sk_buff *skb)
+void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
+ struct sk_buff *skb)
{
napi_gro_receive(&q_vector->napi, skb);
}
@@ -1782,7 +1784,7 @@
static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
struct sk_buff *skb)
{
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned char *va;
unsigned int pull_len;
@@ -1797,14 +1799,14 @@
* we need the header to contain the greater of either ETH_HLEN or
* 60 bytes if the skb->len is less than 60 for skb_pad.
*/
- pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
+ pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
/* update all of the pointers */
skb_frag_size_sub(frag, pull_len);
- frag->page_offset += pull_len;
+ skb_frag_off_add(frag, pull_len);
skb->data_len -= pull_len;
skb->tail += pull_len;
}
@@ -1832,11 +1834,11 @@
skb_headlen(skb),
DMA_FROM_DEVICE);
} else {
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
dma_sync_single_range_for_cpu(rx_ring->dev,
IXGBE_CB(skb)->dma,
- frag->page_offset,
+ skb_frag_off(frag),
skb_frag_size(frag),
DMA_FROM_DEVICE);
}
@@ -1872,9 +1874,9 @@
*
* Returns true if an error was encountered and skb was freed.
**/
-static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
- union ixgbe_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
{
struct net_device *netdev = rx_ring->netdev;
@@ -2103,10 +2105,8 @@
struct sk_buff *skb;
/* prefetch first cache line of first page */
- prefetch(xdp->data);
-#if L1_CACHE_BYTES < 128
- prefetch(xdp->data + L1_CACHE_BYTES);
-#endif
+ net_prefetch(xdp->data);
+
/* Note, we get here by enabling legacy-rx via:
*
* ethtool --set-priv-flags <dev> legacy-rx on
@@ -2169,10 +2169,7 @@
* likely have a consumer accessing first few bytes of meta
* data, and then actual data.
*/
- prefetch(xdp->data_meta);
-#if L1_CACHE_BYTES < 128
- prefetch(xdp->data_meta + L1_CACHE_BYTES);
-#endif
+ net_prefetch(xdp->data_meta);
/* build an skb to around the page buffer */
skb = build_skb(xdp->data_hard_start, truesize);
@@ -2199,14 +2196,6 @@
return skb;
}
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED BIT(0)
-#define IXGBE_XDP_TX BIT(1)
-#define IXGBE_XDP_REDIR BIT(2)
-
-static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_frame *xdpf);
-
static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring,
struct xdp_buff *xdp)
@@ -2229,26 +2218,26 @@
case XDP_PASS:
break;
case XDP_TX:
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf)) {
- result = IXGBE_XDP_CONSUMED;
- break;
- }
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+ goto out_failure;
result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+ if (result == IXGBE_XDP_CONSUMED)
+ goto out_failure;
break;
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
- if (!err)
- result = IXGBE_XDP_REDIR;
- else
- result = IXGBE_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
+ result = IXGBE_XDP_REDIR;
break;
default:
bpf_warn_invalid_xdp_action(act);
- /* fallthrough */
+ fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
- /* fallthrough -- handle aborts by dropping packet */
+ fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
result = IXGBE_XDP_CONSUMED;
break;
@@ -2258,20 +2247,30 @@
return ERR_PTR(-result);
}
+static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring,
+ unsigned int size)
+{
+ unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+ truesize = ixgbe_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+ truesize = ring_uses_build_skb(rx_ring) ?
+ SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+ SKB_DATA_ALIGN(size);
+#endif
+ return truesize;
+}
+
static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
struct ixgbe_rx_buffer *rx_buffer,
unsigned int size)
{
+ unsigned int truesize = ixgbe_rx_frame_truesize(rx_ring, size);
#if (PAGE_SIZE < 8192)
- unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
-
rx_buffer->page_offset ^= truesize;
#else
- unsigned int truesize = ring_uses_build_skb(rx_ring) ?
- SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
- SKB_DATA_ALIGN(size);
-
rx_buffer->page_offset += truesize;
#endif
}
@@ -2304,6 +2303,11 @@
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
+
+ /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+#if (PAGE_SIZE < 8192)
+ xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0);
+#endif
while (likely(total_rx_packets < budget)) {
union ixgbe_adv_rx_desc *rx_desc;
@@ -2339,7 +2343,10 @@
xdp.data_hard_start = xdp.data -
ixgbe_rx_offset(rx_ring);
xdp.data_end = xdp.data + size;
-
+#if (PAGE_SIZE > 4096)
+ /* At larger PAGE_SIZE, frame_sz depend on len size */
+ xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size);
+#endif
skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
}
@@ -2970,35 +2977,6 @@
/* skip the flush */
}
-static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
- u64 qmask)
-{
- u32 mask;
- struct ixgbe_hw *hw = &adapter->hw;
-
- switch (hw->mac.type) {
- case ixgbe_mac_82598EB:
- mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
- IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask);
- break;
- case ixgbe_mac_82599EB:
- case ixgbe_mac_X540:
- case ixgbe_mac_X550:
- case ixgbe_mac_X550EM_x:
- case ixgbe_mac_x550em_a:
- mask = (qmask & 0xFFFFFFFF);
- if (mask)
- IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask);
- mask = (qmask >> 32);
- if (mask)
- IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask);
- break;
- default:
- break;
- }
- /* skip the flush */
-}
-
/**
* ixgbe_irq_enable - Enable default interrupt generation settings
* @adapter: board private structure
@@ -3035,7 +3013,7 @@
case ixgbe_mac_82599EB:
mask |= IXGBE_EIMS_GPI_SDP1(hw);
mask |= IXGBE_EIMS_GPI_SDP2(hw);
- /* fall through */
+ fallthrough;
case ixgbe_mac_X540:
case ixgbe_mac_X550:
case ixgbe_mac_X550EM_x:
@@ -3184,7 +3162,11 @@
#endif
ixgbe_for_each_ring(ring, q_vector->tx) {
- if (!ixgbe_clean_tx_irq(q_vector, ring, budget))
+ bool wd = ring->xsk_pool ?
+ ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) :
+ ixgbe_clean_tx_irq(q_vector, ring, budget);
+
+ if (!wd)
clean_complete = false;
}
@@ -3200,7 +3182,10 @@
per_ring_budget = budget;
ixgbe_for_each_ring(ring, q_vector->rx) {
- int cleaned = ixgbe_clean_rx_irq(q_vector, ring,
+ int cleaned = ring->xsk_pool ?
+ ixgbe_clean_rx_irq_zc(q_vector, ring,
+ per_ring_budget) :
+ ixgbe_clean_rx_irq(q_vector, ring,
per_ring_budget);
work_done += cleaned;
@@ -3334,7 +3319,7 @@
switch (hw->mac.type) {
case ixgbe_mac_82599EB:
ixgbe_check_sfp_event(adapter, eicr);
- /* Fall through */
+ fallthrough;
case ixgbe_mac_X540:
case ixgbe_mac_X550:
case ixgbe_mac_X550EM_x:
@@ -3491,6 +3476,10 @@
int wait_loop = 10;
u32 txdctl = IXGBE_TXDCTL_ENABLE;
u8 reg_idx = ring->reg_idx;
+
+ ring->xsk_pool = NULL;
+ if (ring_is_xdp(ring))
+ ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
/* disable queue to avoid issues while updating state */
IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
@@ -3730,10 +3719,26 @@
srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
/* configure the packet buffer length */
- if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state))
+ if (rx_ring->xsk_pool) {
+ u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool);
+
+ /* If the MAC support setting RXDCTL.RLPML, the
+ * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
+ * RXDCTL.RLPML is set to the actual UMEM buffer
+ * size. If not, then we are stuck with a 1k buffer
+ * size resolution. In this case frames larger than
+ * the UMEM buffer size viewed in a 1k resolution will
+ * be dropped.
+ */
+ if (hw->mac.type != ixgbe_mac_82599EB)
+ srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ else
+ srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ } else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) {
srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
- else
+ } else {
srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ }
/* configure descriptor type */
srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
@@ -4059,6 +4064,18 @@
u32 rxdctl;
u8 reg_idx = ring->reg_idx;
+ xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+ ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
+ if (ring->xsk_pool) {
+ WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_XSK_BUFF_POOL,
+ NULL));
+ xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+ } else {
+ WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED, NULL));
+ }
+
/* disable queue to avoid use of these values while updating state */
rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
rxdctl &= ~IXGBE_RXDCTL_ENABLE;
@@ -4108,6 +4125,16 @@
#endif
}
+ if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
+ u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+
+ rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
+ IXGBE_RXDCTL_RLPML_EN);
+ rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN;
+
+ ring->rx_buf_len = xsk_buf_len;
+ }
+
/* initialize rx_buffer_info */
memset(ring->rx_buffer_info, 0,
sizeof(struct ixgbe_rx_buffer) * ring->count);
@@ -4121,7 +4148,10 @@
IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
ixgbe_rx_desc_queue_enable(adapter, ring);
- ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
+ if (ring->xsk_pool)
+ ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring));
+ else
+ ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
}
static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
@@ -4271,7 +4301,6 @@
if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
- clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
continue;
@@ -4312,7 +4341,7 @@
case ixgbe_mac_x550em_a:
if (adapter->num_vfs)
rdrxctl |= IXGBE_RDRXCTL_PSP;
- /* fall through */
+ fallthrough;
case ixgbe_mac_82599EB:
case ixgbe_mac_X540:
/* Disable RSC for ACK packets */
@@ -4971,24 +5000,41 @@
napi_disable(&adapter->q_vector[q_idx]->napi);
}
-static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask)
+static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
struct ixgbe_hw *hw = &adapter->hw;
- u32 vxlanctrl;
+ struct udp_tunnel_info ti;
- if (!(adapter->flags & (IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE |
- IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)))
- return;
+ udp_tunnel_nic_get_port(dev, table, 0, &ti);
+ if (ti.type == UDP_TUNNEL_TYPE_VXLAN)
+ adapter->vxlan_port = ti.port;
+ else
+ adapter->geneve_port = ti.port;
- vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask;
- IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl);
-
- if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK)
- adapter->vxlan_port = 0;
-
- if (mask & IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK)
- adapter->geneve_port = 0;
+ IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL,
+ ntohs(adapter->vxlan_port) |
+ ntohs(adapter->geneve_port) <<
+ IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT);
+ return 0;
}
+
+static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550 = {
+ .sync_table = ixgbe_udp_tunnel_sync,
+ .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
+ .tables = {
+ { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
+ },
+};
+
+static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550em_a = {
+ .sync_table = ixgbe_udp_tunnel_sync,
+ .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
+ .tables = {
+ { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
+ { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+ },
+};
#ifdef CONFIG_IXGBE_DCB
/**
@@ -5252,6 +5298,11 @@
u16 i = rx_ring->next_to_clean;
struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
+ if (rx_ring->xsk_pool) {
+ ixgbe_xsk_clean_rx_ring(rx_ring);
+ goto skip_free;
+ }
+
/* Free all the Rx ring sk_buffs */
while (i != rx_ring->next_to_alloc) {
if (rx_buffer->skb) {
@@ -5290,6 +5341,7 @@
}
}
+skip_free:
rx_ring->next_to_alloc = 0;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
@@ -5350,9 +5402,10 @@
return err;
}
-static int ixgbe_macvlan_up(struct net_device *vdev, void *data)
+static int ixgbe_macvlan_up(struct net_device *vdev,
+ struct netdev_nested_priv *priv)
{
- struct ixgbe_adapter *adapter = data;
+ struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
struct ixgbe_fwd_adapter *accel;
if (!netif_is_macvlan(vdev))
@@ -5369,8 +5422,12 @@
static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)adapter,
+ };
+
netdev_walk_all_upper_dev_rcu(adapter->netdev,
- ixgbe_macvlan_up, adapter);
+ ixgbe_macvlan_up, &priv);
}
static void ixgbe_configure(struct ixgbe_adapter *adapter)
@@ -5472,9 +5529,17 @@
return ret;
speed = hw->phy.autoneg_advertised;
- if ((!speed) && (hw->mac.ops.get_link_capabilities))
+ if (!speed && hw->mac.ops.get_link_capabilities) {
ret = hw->mac.ops.get_link_capabilities(hw, &speed,
&autoneg);
+ /* remove NBASE-T speeds from default autonegotiation
+ * to accommodate broken network switches in the field
+ * which cannot cope with advertised NBASE-T speeds
+ */
+ speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |
+ IXGBE_LINK_SPEED_2_5GB_FULL);
+ }
+
if (ret)
return ret;
@@ -5627,7 +5692,6 @@
void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
{
- WARN_ON(in_interrupt());
/* put off any impending NetWatchDogTimeout */
netif_trans_update(adapter->netdev);
@@ -5856,7 +5920,7 @@
IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
~IXGBE_DMATXCTL_TE));
- /* fall through */
+ fallthrough;
default:
break;
}
@@ -5934,6 +5998,11 @@
u16 i = tx_ring->next_to_clean;
struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+ if (tx_ring->xsk_pool) {
+ ixgbe_xsk_clean_tx_ring(tx_ring);
+ goto out;
+ }
+
while (i != tx_ring->next_to_use) {
union ixgbe_adv_tx_desc *eop_desc, *tx_desc;
@@ -5985,6 +6054,7 @@
if (!ring_is_xdp(tx_ring))
netdev_tx_reset_queue(txring_txq(tx_ring));
+out:
/* reset next_to_use and next_to_clean */
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
@@ -6053,9 +6123,9 @@
/* Disable Rx */
ixgbe_disable_rx(adapter);
- /* synchronize_sched() needed for pending XDP buffers to drain */
+ /* synchronize_rcu() needed for pending XDP buffers to drain */
if (adapter->xdp_ring[0])
- synchronize_sched();
+ synchronize_rcu();
ixgbe_irq_disable(adapter);
@@ -6124,8 +6194,9 @@
/**
* ixgbe_tx_timeout - Respond to a Tx Hang
* @netdev: network interface device structure
+ * @txqueue: queue number that timed out
**/
-static void ixgbe_tx_timeout(struct net_device *netdev)
+static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
@@ -6259,6 +6330,10 @@
if (ixgbe_init_rss_key(adapter))
return -ENOMEM;
+ adapter->af_xdp_zc_qps = bitmap_zalloc(MAX_XDP_QUEUES, GFP_KERNEL);
+ if (!adapter->af_xdp_zc_qps)
+ return -ENOMEM;
+
/* Set MAC specific capability flags and exceptions */
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
@@ -6289,7 +6364,6 @@
adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
break;
case ixgbe_mac_x550em_a:
- adapter->flags |= IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE;
switch (hw->device_id) {
case IXGBE_DEV_ID_X550EM_A_1G_T:
case IXGBE_DEV_ID_X550EM_A_1G_T_L:
@@ -6298,7 +6372,7 @@
default:
break;
}
- /* fall through */
+ fallthrough;
case ixgbe_mac_X550EM_x:
#ifdef CONFIG_IXGBE_DCB
adapter->flags &= ~IXGBE_FLAG_DCB_CAPABLE;
@@ -6309,14 +6383,13 @@
adapter->fcoe.up = 0;
#endif /* IXGBE_DCB */
#endif /* IXGBE_FCOE */
- /* Fall Through */
+ fallthrough;
case ixgbe_mac_X550:
if (hw->mac.type == ixgbe_mac_X550)
adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
#ifdef CONFIG_IXGBE_DCA
adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE;
#endif
- adapter->flags |= IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE;
break;
default:
break;
@@ -6329,6 +6402,9 @@
#endif
/* n-tuple support exists, always init our spinlock */
spin_lock_init(&adapter->fdir_perfect_lock);
+
+ /* init spinlock to avoid concurrency of VF resources */
+ spin_lock_init(&adapter->vfs_lock);
#ifdef CONFIG_IXGBE_DCB
ixgbe_init_dcb(adapter);
@@ -6390,7 +6466,7 @@
{
struct device *dev = tx_ring->dev;
int orig_node = dev_to_node(dev);
- int ring_node = -1;
+ int ring_node = NUMA_NO_NODE;
int size;
size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -6484,8 +6560,8 @@
{
struct device *dev = rx_ring->dev;
int orig_node = dev_to_node(dev);
- int ring_node = -1;
- int size, err;
+ int ring_node = NUMA_NO_NODE;
+ int size;
size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
@@ -6521,13 +6597,6 @@
if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
rx_ring->queue_index) < 0)
goto err;
-
- err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq,
- MEM_TYPE_PAGE_SHARED, NULL);
- if (err) {
- xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
- goto err;
- }
rx_ring->xdp_prog = adapter->xdp_prog;
@@ -6660,6 +6729,18 @@
}
/**
+ * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @adapter: device handle, pointer to adapter
+ */
+static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
+{
+ if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
+ return IXGBE_RXBUFFER_2K;
+ else
+ return IXGBE_RXBUFFER_3K;
+}
+
+/**
* ixgbe_change_mtu - Change the Maximum Transfer Unit
* @netdev: network interface device structure
* @new_mtu: new value for maximum frame size
@@ -6670,18 +6751,12 @@
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- if (adapter->xdp_prog) {
- int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN +
- VLAN_HLEN;
- int i;
+ if (ixgbe_enabled_xdp_adapter(adapter)) {
+ int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
- for (i = 0; i < adapter->num_rx_queues; i++) {
- struct ixgbe_ring *ring = adapter->rx_ring[i];
-
- if (new_frame_size > ixgbe_rx_bufsz(ring)) {
- e_warn(probe, "Requested MTU size is not supported with XDP\n");
- return -EINVAL;
- }
+ if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) {
+ e_warn(probe, "Requested MTU size is not supported with XDP\n");
+ return -EINVAL;
}
}
@@ -6695,7 +6770,8 @@
(new_mtu > ETH_DATA_LEN))
e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n");
- e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);
+ netdev_dbg(netdev, "changing MTU from %d to %d\n",
+ netdev->mtu, new_mtu);
/* must set new MTU before calling down or up */
netdev->mtu = new_mtu;
@@ -6761,8 +6837,7 @@
ixgbe_up_complete(adapter);
- ixgbe_clear_udp_tunnel_port(adapter, IXGBE_VXLANCTRL_ALL_UDPPORT_MASK);
- udp_tunnel_get_rx_info(netdev);
+ udp_tunnel_nic_reset_ntf(netdev);
return 0;
@@ -6826,21 +6901,14 @@
return 0;
}
-#ifdef CONFIG_PM
-static int ixgbe_resume(struct pci_dev *pdev)
+static int __maybe_unused ixgbe_resume(struct device *dev_d)
{
+ struct pci_dev *pdev = to_pci_dev(dev_d);
struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
struct net_device *netdev = adapter->netdev;
u32 err;
adapter->hw.hw_addr = adapter->io_addr;
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- /*
- * pci_restore_state clears dev->state_saved so call
- * pci_save_state to restore it.
- */
- pci_save_state(pdev);
err = pci_enable_device_mem(pdev);
if (err) {
@@ -6851,7 +6919,7 @@
clear_bit(__IXGBE_DISABLED, &adapter->state);
pci_set_master(pdev);
- pci_wake_from_d3(pdev, false);
+ device_wakeup_disable(dev_d);
ixgbe_reset(adapter);
@@ -6869,7 +6937,6 @@
return err;
}
-#endif /* CONFIG_PM */
static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
{
@@ -6878,9 +6945,6 @@
struct ixgbe_hw *hw = &adapter->hw;
u32 ctrl;
u32 wufc = adapter->wol;
-#ifdef CONFIG_PM
- int retval = 0;
-#endif
rtnl_lock();
netif_device_detach(netdev);
@@ -6891,12 +6955,6 @@
ixgbe_clear_interrupt_scheme(adapter);
rtnl_unlock();
-#ifdef CONFIG_PM
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-
-#endif
if (hw->mac.ops.stop_link_on_d3)
hw->mac.ops.stop_link_on_d3(hw);
@@ -6951,26 +7009,18 @@
return 0;
}
-#ifdef CONFIG_PM
-static int ixgbe_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused ixgbe_suspend(struct device *dev_d)
{
+ struct pci_dev *pdev = to_pci_dev(dev_d);
int retval;
bool wake;
retval = __ixgbe_shutdown(pdev, &wake);
- if (retval)
- return retval;
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
+ device_set_wakeup_enable(dev_d, wake);
- return 0;
+ return retval;
}
-#endif /* CONFIG_PM */
static void ixgbe_shutdown(struct pci_dev *pdev)
{
@@ -7135,7 +7185,7 @@
hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC);
hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC);
hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC);
- /* fall through */
+ fallthrough;
case ixgbe_mac_82599EB:
for (i = 0; i < 16; i++)
adapter->hw_rx_no_dma_resources +=
@@ -7834,6 +7884,33 @@
}
/**
+ * ixgbe_check_fw_error - Check firmware for errors
+ * @adapter: the adapter private structure
+ *
+ * Check firmware errors in register FWSM
+ */
+static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 fwsm;
+
+ /* read fwsm.ext_err_ind register and log errors */
+ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+
+ if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
+ !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
+ e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
+ fwsm);
+
+ if (hw->mac.ops.fw_recovery_mode && hw->mac.ops.fw_recovery_mode(hw)) {
+ e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+ return true;
+ }
+
+ return false;
+}
+
+/**
* ixgbe_service_task - manages and runs subtasks
* @work: pointer to work_struct containing our data
**/
@@ -7851,11 +7928,11 @@
ixgbe_service_event_complete(adapter);
return;
}
- if (adapter->flags2 & IXGBE_FLAG2_UDP_TUN_REREG_NEEDED) {
- rtnl_lock();
- adapter->flags2 &= ~IXGBE_FLAG2_UDP_TUN_REREG_NEEDED;
- udp_tunnel_get_rx_info(adapter->netdev);
- rtnl_unlock();
+ if (ixgbe_check_fw_error(adapter)) {
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ unregister_netdev(adapter->netdev);
+ ixgbe_service_event_complete(adapter);
+ return;
}
ixgbe_reset_subtask(adapter);
ixgbe_phy_interrupt_subtask(adapter);
@@ -7890,6 +7967,7 @@
} ip;
union {
struct tcphdr *tcp;
+ struct udphdr *udp;
unsigned char *hdr;
} l4;
u32 paylen, l4_offset;
@@ -7913,7 +7991,8 @@
l4.hdr = skb_checksum_start(skb);
/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
- type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
+ type_tucmd = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
+ IXGBE_ADVTXD_TUCMD_L4T_UDP : IXGBE_ADVTXD_TUCMD_L4T_TCP;
/* initialize outer IP header fields */
if (ip.v4->version == 4) {
@@ -7943,12 +8022,20 @@
/* determine offset of inner transport header */
l4_offset = l4.hdr - skb->data;
- /* compute length of segmentation header */
- *hdr_len = (l4.tcp->doff * 4) + l4_offset;
-
/* remove payload length from inner checksum */
paylen = skb->len - l4_offset;
- csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
+
+ if (type_tucmd & IXGBE_ADVTXD_TUCMD_L4T_TCP) {
+ /* compute length of segmentation header */
+ *hdr_len = (l4.tcp->doff * 4) + l4_offset;
+ csum_replace_by_diff(&l4.tcp->check,
+ (__force __wsum)htonl(paylen));
+ } else {
+ /* compute length of segmentation header */
+ *hdr_len = sizeof(*l4.udp) + l4_offset;
+ csum_replace_by_diff(&l4.udp->check,
+ (__force __wsum)htonl(paylen));
+ }
/* update gso size and bytecount with header size */
first->gso_segs = skb_shinfo(skb)->gso_segs;
@@ -8001,7 +8088,7 @@
switch (skb->csum_offset) {
case offsetof(struct tcphdr, check):
type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
- /* fall through */
+ fallthrough;
case offsetof(struct udphdr, check):
break;
case offsetof(struct sctphdr, checksum):
@@ -8013,7 +8100,7 @@
type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_SCTP;
break;
}
- /* fall through */
+ fallthrough;
default:
skb_checksum_help(skb);
goto csum_failed;
@@ -8125,9 +8212,6 @@
return __ixgbe_maybe_stop_tx(tx_ring, size);
}
-#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
- IXGBE_TXD_CMD_RS)
-
static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
struct ixgbe_tx_buffer *first,
const u8 hdr_len)
@@ -8135,7 +8219,7 @@
struct sk_buff *skb = first->skb;
struct ixgbe_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
- struct skb_frag_struct *frag;
+ skb_frag_t *frag;
dma_addr_t dma;
unsigned int data_len, size;
u32 tx_flags = first->tx_flags;
@@ -8227,6 +8311,8 @@
/* set the timestamp */
first->time_stamp = jiffies;
+ skb_tx_timestamp(skb);
+
/*
* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch. (Only applicable for weak-ordered
@@ -8248,13 +8334,8 @@
ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
-
- /* we need this if more than one processor can write to our tail
- * at a time, it synchronizes IO on IA64/Altix systems
- */
- mmiowb();
}
return 0;
@@ -8328,7 +8409,7 @@
struct ixgbe_adapter *adapter = q_vector->adapter;
if (unlikely(skb_tail_pointer(skb) < hdr.network +
- VXLAN_HEADROOM))
+ vxlan_headroom(0)))
return;
/* verify the port is recognized as VXLAN */
@@ -8434,8 +8515,7 @@
#ifdef IXGBE_FCOE
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
- struct net_device *sb_dev,
- select_queue_fallback_t fallback)
+ struct net_device *sb_dev)
{
struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
@@ -8463,9 +8543,9 @@
if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
break;
- /* fall through */
+ fallthrough;
default:
- return fallback(dev, skb, sb_dev);
+ return netdev_pick_tx(dev, skb, sb_dev);
}
f = &adapter->ring_feature[RING_F_FCOE];
@@ -8480,8 +8560,8 @@
}
#endif
-static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
- struct xdp_frame *xdpf)
+int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
+ struct xdp_frame *xdpf)
{
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
struct ixgbe_tx_buffer *tx_buffer;
@@ -8558,7 +8638,8 @@
* otherwise try next time
*/
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
- count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+ count += TXD_USE_COUNT(skb_frag_size(
+ &skb_shinfo(skb)->frags[f]));
if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) {
tx_ring->tx_stats.tx_busy++;
@@ -8604,8 +8685,6 @@
adapter->tx_hwtstamp_skipped++;
}
}
-
- skb_tx_timestamp(skb);
#ifdef CONFIG_PCI_IOV
/*
@@ -8653,7 +8732,7 @@
#endif /* IXGBE_FCOE */
-#ifdef CONFIG_XFRM_OFFLOAD
+#ifdef CONFIG_IXGBE_IPSEC
if (xfrm_offload(skb) &&
!ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
goto out_drop;
@@ -8704,7 +8783,9 @@
if (skb_put_padto(skb, 17))
return NETDEV_TX_OK;
- tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping];
+ tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)];
+ if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state)))
+ return NETDEV_TX_BUSY;
return ixgbe_xmit_frame_ring(skb, adapter, tx_ring);
}
@@ -8747,6 +8828,15 @@
u16 value;
int rc;
+ if (adapter->mii_bus) {
+ int regnum = addr;
+
+ if (devad != MDIO_DEVAD_NONE)
+ regnum |= (devad << 16) | MII_ADDR_C45;
+
+ return mdiobus_read(adapter->mii_bus, prtad, regnum);
+ }
+
if (prtad != hw->phy.mdio.prtad)
return -EINVAL;
rc = hw->phy.ops.read_reg(hw, addr, devad, &value);
@@ -8760,6 +8850,15 @@
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
+
+ if (adapter->mii_bus) {
+ int regnum = addr;
+
+ if (devad != MDIO_DEVAD_NONE)
+ regnum |= (devad << 16) | MII_ADDR_C45;
+
+ return mdiobus_write(adapter->mii_bus, prtad, regnum, value);
+ }
if (prtad != hw->phy.mdio.prtad)
return -EINVAL;
@@ -8778,7 +8877,7 @@
case SIOCGMIIPHY:
if (!adapter->hw.phy.ops.read_reg)
return -EOPNOTSUPP;
- /* fall through */
+ fallthrough;
default:
return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd);
}
@@ -8953,9 +9052,10 @@
}
#endif /* CONFIG_IXGBE_DCB */
-static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
+static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
+ struct netdev_nested_priv *priv)
{
- struct ixgbe_adapter *adapter = data;
+ struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
struct ixgbe_fwd_adapter *accel;
int pool;
@@ -8992,13 +9092,16 @@
static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
+ struct netdev_nested_priv priv = {
+ .data = (void *)adapter,
+ };
/* flush any stale bits out of the fwd bitmask */
bitmap_clear(adapter->fwd_bitmask, 1, 63);
/* walk through upper devices reassigning pools */
netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool,
- adapter);
+ &priv);
}
/**
@@ -9172,14 +9275,18 @@
u8 queue;
};
-static int get_macvlan_queue(struct net_device *upper, void *_data)
+static int get_macvlan_queue(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
if (netif_is_macvlan(upper)) {
struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper);
- struct upper_walk_data *data = _data;
- struct ixgbe_adapter *adapter = data->adapter;
- int ifindex = data->ifindex;
+ struct ixgbe_adapter *adapter;
+ struct upper_walk_data *data;
+ int ifindex;
+ data = (struct upper_walk_data *)priv->data;
+ ifindex = data->ifindex;
+ adapter = data->adapter;
if (vadapter && upper->ifindex == ifindex) {
data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
data->action = data->queue;
@@ -9195,6 +9302,7 @@
{
struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
unsigned int num_vfs = adapter->num_vfs, vf;
+ struct netdev_nested_priv priv;
struct upper_walk_data data;
struct net_device *upper;
@@ -9214,8 +9322,9 @@
data.ifindex = ifindex;
data.action = 0;
data.queue = 0;
+ priv.data = (void *)&data;
if (netdev_walk_all_upper_dev_rcu(adapter->netdev,
- get_macvlan_queue, &data)) {
+ get_macvlan_queue, &priv)) {
*action = data.action;
*queue = data.queue;
@@ -9426,6 +9535,10 @@
jump->mat = nexthdr[i].jump;
adapter->jump_tables[link_uhtid] = jump;
break;
+ } else {
+ kfree(mask);
+ kfree(input);
+ kfree(jump);
}
}
return 0;
@@ -9545,27 +9658,6 @@
}
}
-static int ixgbe_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int ixgbe_setup_tc_mqprio(struct net_device *dev,
struct tc_mqprio_qopt *mqprio)
{
@@ -9573,12 +9665,19 @@
return ixgbe_setup_tc(dev, mqprio->num_tc);
}
+static LIST_HEAD(ixgbe_block_cb_list);
+
static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return ixgbe_setup_tc_block(dev, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &ixgbe_block_cb_list,
+ ixgbe_setup_tc_block_cb,
+ adapter, adapter, true);
case TC_SETUP_QDISC_MQPRIO:
return ixgbe_setup_tc_mqprio(dev, type_data);
default:
@@ -9704,26 +9803,6 @@
netdev->features = features;
- if ((adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) {
- if (features & NETIF_F_RXCSUM) {
- adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED;
- } else {
- u32 port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK;
-
- ixgbe_clear_udp_tunnel_port(adapter, port_mask);
- }
- }
-
- if ((adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) {
- if (features & NETIF_F_RXCSUM) {
- adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED;
- } else {
- u32 port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK;
-
- ixgbe_clear_udp_tunnel_port(adapter, port_mask);
- }
- }
-
if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1)
ixgbe_reset_l2fw_offload(adapter);
else if (need_reset)
@@ -9732,125 +9811,14 @@
NETIF_F_HW_VLAN_CTAG_FILTER))
ixgbe_set_rx_mode(netdev);
- return 0;
-}
-
-/**
- * ixgbe_add_udp_tunnel_port - Get notifications about adding UDP tunnel ports
- * @dev: The port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void ixgbe_add_udp_tunnel_port(struct net_device *dev,
- struct udp_tunnel_info *ti)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
- struct ixgbe_hw *hw = &adapter->hw;
- __be16 port = ti->port;
- u32 port_shift = 0;
- u32 reg;
-
- if (ti->sa_family != AF_INET)
- return;
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
- return;
-
- if (adapter->vxlan_port == port)
- return;
-
- if (adapter->vxlan_port) {
- netdev_info(dev,
- "VXLAN port %d set, not adding port %d\n",
- ntohs(adapter->vxlan_port),
- ntohs(port));
- return;
- }
-
- adapter->vxlan_port = port;
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))
- return;
-
- if (adapter->geneve_port == port)
- return;
-
- if (adapter->geneve_port) {
- netdev_info(dev,
- "GENEVE port %d set, not adding port %d\n",
- ntohs(adapter->geneve_port),
- ntohs(port));
- return;
- }
-
- port_shift = IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT;
- adapter->geneve_port = port;
- break;
- default:
- return;
- }
-
- reg = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) | ntohs(port) << port_shift;
- IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, reg);
-}
-
-/**
- * ixgbe_del_udp_tunnel_port - Get notifications about removing UDP tunnel ports
- * @dev: The port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void ixgbe_del_udp_tunnel_port(struct net_device *dev,
- struct udp_tunnel_info *ti)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
- u32 port_mask;
-
- if (ti->type != UDP_TUNNEL_TYPE_VXLAN &&
- ti->type != UDP_TUNNEL_TYPE_GENEVE)
- return;
-
- if (ti->sa_family != AF_INET)
- return;
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
- return;
-
- if (adapter->vxlan_port != ti->port) {
- netdev_info(dev, "VXLAN port %d not found\n",
- ntohs(ti->port));
- return;
- }
-
- port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK;
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))
- return;
-
- if (adapter->geneve_port != ti->port) {
- netdev_info(dev, "GENEVE port %d not found\n",
- ntohs(ti->port));
- return;
- }
-
- port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK;
- break;
- default:
- return;
- }
-
- ixgbe_clear_udp_tunnel_port(adapter, port_mask);
- adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED;
+ return 1;
}
static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
/* guarantee we can provide a unique filter for the unicast address */
if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -9939,7 +9907,8 @@
}
static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags)
+ struct nlmsghdr *nlh, u16 flags,
+ struct netlink_ext_ack *extack)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct nlattr *attr, *br_spec;
@@ -10133,6 +10102,7 @@
if (unlikely(mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN))
return features & ~(NETIF_F_HW_CSUM |
NETIF_F_SCTP_CRC |
+ NETIF_F_GSO_UDP_L4 |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_TSO |
NETIF_F_TSO6);
@@ -10141,6 +10111,7 @@
if (unlikely(network_hdr_len > IXGBE_MAX_NETWORK_HDR_LEN))
return features & ~(NETIF_F_HW_CSUM |
NETIF_F_SCTP_CRC |
+ NETIF_F_GSO_UDP_L4 |
NETIF_F_TSO |
NETIF_F_TSO6);
@@ -10150,8 +10121,8 @@
* the TSO, so it's the exception.
*/
if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
-#ifdef CONFIG_XFRM_OFFLOAD
- if (!skb->sp)
+#ifdef CONFIG_IXGBE_IPSEC
+ if (!secpath_exists(skb))
#endif
features &= ~NETIF_F_TSO;
}
@@ -10164,6 +10135,8 @@
int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct bpf_prog *old_prog;
+ bool need_reset;
+ int num_queues;
if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
return -EINVAL;
@@ -10186,10 +10159,16 @@
return -ENOMEM;
old_prog = xchg(&adapter->xdp_prog, prog);
+ need_reset = (!!prog != !!old_prog);
/* If transitioning XDP modes reconfigure rings */
- if (!!prog != !!old_prog) {
- int err = ixgbe_setup_tc(dev, adapter->hw_tcs);
+ if (need_reset) {
+ int err;
+
+ if (!prog)
+ /* Wait until ndo_xsk_wakeup completes. */
+ synchronize_rcu();
+ err = ixgbe_setup_tc(dev, adapter->hw_tcs);
if (err) {
rcu_assign_pointer(adapter->xdp_prog, old_prog);
@@ -10204,6 +10183,18 @@
if (old_prog)
bpf_prog_put(old_prog);
+ /* Kick start the NAPI context if there is an AF_XDP socket open
+ * on that queue id. This so that receiving will start.
+ */
+ if (need_reset && prog) {
+ num_queues = min_t(int, adapter->num_rx_queues,
+ adapter->num_xdp_queues);
+ for (i = 0; i < num_queues; i++)
+ if (adapter->xdp_ring[i]->xsk_pool)
+ (void)ixgbe_xsk_wakeup(adapter->netdev, i,
+ XDP_WAKEUP_RX);
+ }
+
return 0;
}
@@ -10214,16 +10205,16 @@
switch (xdp->command) {
case XDP_SETUP_PROG:
return ixgbe_xdp_setup(dev, xdp->prog);
- case XDP_QUERY_PROG:
- xdp->prog_id = adapter->xdp_prog ?
- adapter->xdp_prog->aux->id : 0;
- return 0;
+ case XDP_SETUP_XSK_POOL:
+ return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool,
+ xdp->xsk.queue_id);
+
default:
return -EINVAL;
}
}
-static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
+void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
{
/* Force memory writes to complete before letting h/w know there
* are new descriptors to fetch.
@@ -10251,6 +10242,9 @@
*/
ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL;
if (unlikely(!ring))
+ return -ENXIO;
+
+ if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state)))
return -ENXIO;
for (i = 0; i < n; i++) {
@@ -10309,12 +10303,167 @@
.ndo_bridge_getlink = ixgbe_ndo_bridge_getlink,
.ndo_dfwd_add_station = ixgbe_fwd_add,
.ndo_dfwd_del_station = ixgbe_fwd_del,
- .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port,
- .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port,
+ .ndo_udp_tunnel_add = udp_tunnel_nic_add_port,
+ .ndo_udp_tunnel_del = udp_tunnel_nic_del_port,
.ndo_features_check = ixgbe_features_check,
.ndo_bpf = ixgbe_xdp,
.ndo_xdp_xmit = ixgbe_xdp_xmit,
+ .ndo_xsk_wakeup = ixgbe_xsk_wakeup,
};
+
+static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring)
+{
+ unsigned long wait_delay, delay_interval;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u8 reg_idx = tx_ring->reg_idx;
+ int wait_loop;
+ u32 txdctl;
+
+ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+
+ /* delay mechanism from ixgbe_disable_tx */
+ delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+ wait_loop = IXGBE_MAX_RX_DESC_POLL;
+ wait_delay = delay_interval;
+
+ while (wait_loop--) {
+ usleep_range(wait_delay, wait_delay + 10);
+ wait_delay += delay_interval * 2;
+ txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+
+ if (!(txdctl & IXGBE_TXDCTL_ENABLE))
+ return;
+ }
+
+ e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n");
+}
+
+static void ixgbe_disable_txr(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring)
+{
+ set_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
+ ixgbe_disable_txr_hw(adapter, tx_ring);
+}
+
+static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *rx_ring)
+{
+ unsigned long wait_delay, delay_interval;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u8 reg_idx = rx_ring->reg_idx;
+ int wait_loop;
+ u32 rxdctl;
+
+ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+ rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+ rxdctl |= IXGBE_RXDCTL_SWFLSH;
+
+ /* write value back with RXDCTL.ENABLE bit cleared */
+ IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+
+ /* RXDCTL.EN may not change on 82598 if link is down, so skip it */
+ if (hw->mac.type == ixgbe_mac_82598EB &&
+ !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+ return;
+
+ /* delay mechanism from ixgbe_disable_rx */
+ delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+ wait_loop = IXGBE_MAX_RX_DESC_POLL;
+ wait_delay = delay_interval;
+
+ while (wait_loop--) {
+ usleep_range(wait_delay, wait_delay + 10);
+ wait_delay += delay_interval * 2;
+ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+
+ if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
+ return;
+ }
+
+ e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n");
+}
+
+static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring)
+{
+ memset(&tx_ring->stats, 0, sizeof(tx_ring->stats));
+ memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
+}
+
+static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring)
+{
+ memset(&rx_ring->stats, 0, sizeof(rx_ring->stats));
+ memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
+}
+
+/**
+ * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings
+ * @adapter: adapter structure
+ * @ring: ring index
+ *
+ * This function disables a certain Rx/Tx/XDP Tx ring. The function
+ * assumes that the netdev is running.
+ **/
+void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
+{
+ struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
+
+ rx_ring = adapter->rx_ring[ring];
+ tx_ring = adapter->tx_ring[ring];
+ xdp_ring = adapter->xdp_ring[ring];
+
+ ixgbe_disable_txr(adapter, tx_ring);
+ if (xdp_ring)
+ ixgbe_disable_txr(adapter, xdp_ring);
+ ixgbe_disable_rxr_hw(adapter, rx_ring);
+
+ if (xdp_ring)
+ synchronize_rcu();
+
+ /* Rx/Tx/XDP Tx share the same napi context. */
+ napi_disable(&rx_ring->q_vector->napi);
+
+ ixgbe_clean_tx_ring(tx_ring);
+ if (xdp_ring)
+ ixgbe_clean_tx_ring(xdp_ring);
+ ixgbe_clean_rx_ring(rx_ring);
+
+ ixgbe_reset_txr_stats(tx_ring);
+ if (xdp_ring)
+ ixgbe_reset_txr_stats(xdp_ring);
+ ixgbe_reset_rxr_stats(rx_ring);
+}
+
+/**
+ * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings
+ * @adapter: adapter structure
+ * @ring: ring index
+ *
+ * This function enables a certain Rx/Tx/XDP Tx ring. The function
+ * assumes that the netdev is running.
+ **/
+void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
+{
+ struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
+
+ rx_ring = adapter->rx_ring[ring];
+ tx_ring = adapter->tx_ring[ring];
+ xdp_ring = adapter->xdp_ring[ring];
+
+ /* Rx/Tx/XDP Tx share the same napi context. */
+ napi_enable(&rx_ring->q_vector->napi);
+
+ ixgbe_configure_tx_ring(adapter, tx_ring);
+ if (xdp_ring)
+ ixgbe_configure_tx_ring(adapter, xdp_ring);
+ ixgbe_configure_rx_ring(adapter, rx_ring);
+
+ clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
+ if (xdp_ring)
+ clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+}
/**
* ixgbe_enumerate_functions - Get the number of ports this device has
@@ -10398,7 +10547,7 @@
/* only support first port */
if (hw->bus.func != 0)
break;
- /* fall through */
+ fallthrough;
case IXGBE_SUBDEV_ID_82599_SP_560FLR:
case IXGBE_SUBDEV_ID_82599_SFP:
case IXGBE_SUBDEV_ID_82599_RNDC:
@@ -10600,6 +10749,18 @@
if (err)
goto err_sw_init;
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_X550:
+ case ixgbe_mac_X550EM_x:
+ netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550;
+ break;
+ case ixgbe_mac_x550em_a:
+ netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550em_a;
+ break;
+ default:
+ break;
+ }
+
/* Make sure the SWFW semaphore is in a valid state */
if (hw->mac.ops.init_swfw_sync)
hw->mac.ops.init_swfw_sync(hw);
@@ -10677,9 +10838,9 @@
IXGBE_GSO_PARTIAL_FEATURES;
if (hw->mac.type >= ixgbe_mac_82599EB)
- netdev->features |= NETIF_F_SCTP_CRC;
+ netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_GSO_UDP_L4;
-#ifdef CONFIG_XFRM_OFFLOAD
+#ifdef CONFIG_IXGBE_IPSEC
#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \
NETIF_F_HW_ESP_TX_CSUM | \
NETIF_F_GSO_ESP)
@@ -10753,6 +10914,11 @@
netdev->hw_features |= NETIF_F_LRO;
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
netdev->features |= NETIF_F_LRO;
+
+ if (ixgbe_check_fw_error(adapter)) {
+ err = -EIO;
+ goto err_sw_init;
+ }
/* make sure the EEPROM is good */
if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
@@ -10889,8 +11055,8 @@
*/
if (hw->mac.ops.set_fw_drv_ver)
hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, 0xFF,
- sizeof(ixgbe_driver_version) - 1,
- ixgbe_driver_version);
+ sizeof(UTS_RELEASE) - 1,
+ UTS_RELEASE);
/* add san mac addr to netdev */
ixgbe_add_sanmac_netdev(netdev);
@@ -10910,8 +11076,14 @@
IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
true);
+ err = ixgbe_mii_bus_init(hw);
+ if (err)
+ goto err_netdev;
+
return 0;
+err_netdev:
+ unregister_netdev(netdev);
err_register:
ixgbe_release_hw_control(adapter);
ixgbe_clear_interrupt_scheme(adapter);
@@ -10922,6 +11094,7 @@
kfree(adapter->jump_tables[0]);
kfree(adapter->mac_table);
kfree(adapter->rss_key);
+ bitmap_free(adapter->af_xdp_zc_qps);
err_ioremap:
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
@@ -10961,6 +11134,8 @@
set_bit(__IXGBE_REMOVING, &adapter->state);
cancel_work_sync(&adapter->service_task);
+ if (adapter->mii_bus)
+ mdiobus_unregister(adapter->mii_bus);
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
@@ -11009,6 +11184,7 @@
kfree(adapter->mac_table);
kfree(adapter->rss_key);
+ bitmap_free(adapter->af_xdp_zc_qps);
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
@@ -11114,8 +11290,6 @@
/* Free device reference count */
pci_dev_put(vfdev);
}
-
- pci_cleanup_aer_uncorrect_error_status(pdev);
}
/*
@@ -11165,7 +11339,6 @@
{
struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
pci_ers_result_t result;
- int err;
if (pci_enable_device_mem(pdev)) {
e_err(probe, "Cannot re-enable PCI device after reset.\n");
@@ -11183,13 +11356,6 @@
ixgbe_reset(adapter);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
result = PCI_ERS_RESULT_RECOVERED;
- }
-
- err = pci_cleanup_aer_uncorrect_error_status(pdev);
- if (err) {
- e_dev_err("pci_cleanup_aer_uncorrect_error_status "
- "failed 0x%0x\n", err);
- /* non-fatal, continue */
}
return result;
@@ -11229,16 +11395,15 @@
.resume = ixgbe_io_resume,
};
+static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume);
+
static struct pci_driver ixgbe_driver = {
- .name = ixgbe_driver_name,
- .id_table = ixgbe_pci_tbl,
- .probe = ixgbe_probe,
- .remove = ixgbe_remove,
-#ifdef CONFIG_PM
- .suspend = ixgbe_suspend,
- .resume = ixgbe_resume,
-#endif
- .shutdown = ixgbe_shutdown,
+ .name = ixgbe_driver_name,
+ .id_table = ixgbe_pci_tbl,
+ .probe = ixgbe_probe,
+ .remove = ixgbe_remove,
+ .driver.pm = &ixgbe_pm_ops,
+ .shutdown = ixgbe_shutdown,
.sriov_configure = ixgbe_pci_sriov_configure,
.err_handler = &ixgbe_err_handler
};
@@ -11252,7 +11417,7 @@
static int __init ixgbe_init_module(void)
{
int ret;
- pr_info("%s - version %s\n", ixgbe_driver_string, ixgbe_driver_version);
+ pr_info("%s\n", ixgbe_driver_string);
pr_info("%s\n", ixgbe_copyright);
ixgbe_wq = create_singlethread_workqueue(ixgbe_driver_name);
--
Gitblit v1.6.2